© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 8098
    Prev
    Next
    INDEX
    Explanations

    incidents related to law enforcement and political violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.45
     wherein
    -0.37
    protoimpl
    -0.37
     OMITBAD
    -0.34
     lev
    -0.33
    vič
    -0.33
     godziny
    -0.32
     initComponents
    -0.32
     tal
    -0.31
    fmt
    -0.30
    POSITIVE LOGITS
     Bangladesh
    1.07
    Bangladesh
    1.01
     Dhaka
    0.94
     Banglades
    0.94
     Chowdhury
    0.74
     Bengali
    0.69
     Rohing
    0.68
    ৳
    0.68
     Bang
    0.63
    ẏ
    0.63
    Activations Density 0.119%

    No Known Activations